胡海根(校外副教授)
一、基本信息
工作单位:浙江工业大学
学科/专业:计算机科学与技术/控制理论与控制工程
职称:副教授
职务:无
导师类别:博导/硕导
邮箱:hghu@zjut.edu.cn
二、学习工作经历
2013年1月获得同济大学控制理论与控制工程博士学位,2019年6月从法国鲁昂大学Laboratoire LITIS,Equipe Quantif博士后出站,现为浙江工业大学计算机科学与技术学院副教授,博士生导师,新葡的京集团8814新葡的京集团8814硕士生导师。
三、研究领域
主要从事计算机视觉、医学图像处理、图像分割与目标检测、多目标进化计算等方面的研究。
五、科研课题(限10项)
先后主持国家自然科学基金面上项目、863项目子课题、浙江省自然科学基金以及多项企业横向课题。主持承担的代表性项目有:
(1)国家自然科学基金面上项目:基于域自适应的皮肤镜征象识别及脱发疾病智能诊断模型(项目批准号:62373324),2024.1-2027.12, 65万元(在研)
(2)企业(杭州杰峰科技有限公司)横向项目,面向家居视频监控的视觉理解与大模型加速计算,2024.03-2024.8,76.5万元(在研)
(3)浙江省台州市“500精英计划”:覆膜砂造型浇注制管控于一体智能化生产线(台州市“500精英计划”创业类人才项目B类),2022.01-2026.12, 300万元(在研)
(4)企业(东莞西尼自动化科技有限公司)横向项目,面向电子元器件检测的图像处理算法优化,2020.1-2021.1,15万元(结题)
(5)企业(浙江蓝虹科技有限公司)横向项目,大数据驱动的固废资源循环利用综合评价系统,2020.05-2023.12,300万元(在研)
(6)中科院上海微系统与信息技术研究所基金项目:基于生物特征的步态识别算法研究(项目批准号:SYS201801),2019.10-2020.12,35万元(结题)
(7)浙江省公益技术研究计划:面向临床的黑色素瘤初步筛查与智能诊断关键技术研究(项目批准号:LGF20H180002),2020.1-2022.12,10万元(结题)
(8)浙江省自然科学基金:基于CNN 的相差显微图像序列下的癌细胞检测与多目标跟踪(项目批准号:Y18F030084),2018.1-2019.12,10万元(结题)
(9)国家自然科学基金面上项目:具有区间输出约束的温室环境系统多变量优化控制算法的研究(项目批准号:61374094),2014.1-2017.12, 81万元(结题)
(10)企业(杭州创美实业)横向项目,三相智能型漏电保护器的研发,2013.3-2018.6,45万元(结题)
六、代表性论文和著作(限10项)
先后在IEEE Transactions on Neural Networks and Learning Systems(TNNLS)、Pattern Recognition、Neural Networks、IEEE/ACM Transactions on Computational Biology and Bioinformatics(TCBB)、Applied Soft Computing、Computer Methods and Programs in Biomedicine、Neural Computing and Applications、Neurocomputing、International Journal of Computer Assisted Radiology and Surgery、计算机学报等国内外期刊和ECAI、ECML-PKDD、BIBM、ICASSP等重要国际学术会议上发表论文80多篇,授权国家发明专利40余项。代表性论文:
[1]HaigenHu,AizhuLiu,QiuGuan,XiaoxinLi,ShengyongChen,QianweiZhou.Adaptively Customizing Activation Functions for Various Layers.IEEE Transactions on Neural Networks and Learning Systems,2023,34(9): 6096-6107.(IF 14.255, zjut100,中科院一区TOP期刊).
[2]HaigenHu,LeizhaoShen,QiuGuan,XiaoxinLi,QianweiZhou,SuRuan.Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images. Pattern Recognition, 2022,Vol.124,108452. (IF 8.518,中科院一区TOP期刊).
[3]HaigenHu,ChenghanYu,QianweiZhou,QiuGuan,HailinFeng.HDConv: Heterogeneous kernel-based dilated convolutions.Neural Networks,2024, Vol. 179, 106568.(中科院一区)
[4]TianQiu,HaigenHu(通讯),RuixinChen,QianweiZhou,QiuGuan,XiaoxinLi.A multi-root solver for discontinuous and non-differentiable equations by integrating genetic algorithm and derivative-free iterative methods, Applied Soft Computing, 2021, Vol.109, 107493.(中科院一区,IF 8.263)
[5]HaigenHu,QiuGuan,ShengyongChen(通讯),ZhiweiJi, Lin Yao. Detection and Recognition for Life State of Cell Cancer Using Two-Stage Cascade CNNs. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020, 17(3):887-898.(CCF B国际学术期刊,JCR一区,IF 3.702)
[6]Tongxue Zhou, Su Ruan,Haigen Hu*(通讯).A literature survey of MR-based brain tumor segmentation with missing modalities.Computerized Medical Imaging and Graphics,Vol.104,2023,102167.(IF 7.422,中科院二区)
[7]HaigenHu,AizhuLiu,QianweiZhou,QiuGuan,XiaoxinLi, Qi Chen. An adaptive learning method of anchor shape priors for biological cells detection and segmentation.Computer Methods and Programs in Biomedicine,2021, Vol. 208,106260.(中科院二区,IF7.027)
[8]YujieZhou,HaigenHu,QianweiZhou,QiuGuan andMingfengJiang.Rethinking Domain Generalization from Perspective of Gradient Granularity.27th European Conference on Artificial Intelligence (ECAI-2024),Santiago de Compostela,19-24 October,2024.(CCFB类国际学术会议)
[9]HaigenHu,JingshanHong,KangkangSong,JinweiZhu andWeilunRen.Cut-Stitch:aSimple and Effective Data Augmentation Method for Industrial Inspection.European Conference on MachineLearning and Principles and Practice of Knowledge Discovery in Databases(ECML PKDD 2024),9-13September, 2024,Vilnius.(CCFB类国际学术会议)
[10]KangkangAi,HaigenHu,QianweiZhou andQiuGuan.SGT: Self-Guided Transformer for Few-Shot Semantic Segmentation.ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, 14-19 April,2024, pp. 5935-5939.(CCFB类国际学术会议)
七、获奖情况
2020年获得台州市“500精英”荣誉称号。